© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48325
    Prev
    Next
    INDEX
    Explanations

    program code, punctuation, and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     /
    -2.14
     —
    -1.66
     with
    -1.63
     =
    -1.55
     for
    -1.52
     –
    -1.51
     to
    -1.48
     in
    -1.42
     +
    -1.40
     an
    -1.39
    POSITIVE LOGITS
    😊
    1.51
     diriger
    1.45
     occuper
    1.43
     maniere
    1.42
     participer
    1.42
     plafon
    1.38
     réinitial
    1.38
     sauver
    1.38
     accompagner
    1.36
     Kühlschrank
    1.36
    Activations Density 0.289%

    No Known Activations